© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155894
    Prev
    Next
    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    の種類
    0.38
    .$$
    0.37
     کہتے
    0.37
    ┊
    0.37
    /**
    0.37
    \".
    0.36
     \(
    0.35
    和其他
    0.35
    💙
    0.35
    â
    0.35
    POSITIVE LOGITS
    ̀
    0.48
    了大
    0.41
    了不少
    0.41
    जारत
    0.40
    ังหวัด
    0.40
     una
    0.40
    了一
    0.39
    了一种
    0.39
     ceea
    0.39
    ㅏ
    0.39
    Activations Density 0.003%

    No Known Activations